Research & NLT Lab

Research Interests

My research integrates statistical methodology, data science, and algorithmic decision-making, with applications in spatial analysis, biomedical data, and network traversal. Core areas of interest include:

Statistical machine learning and data science: I develop and analyze network-driven learning algorithms, with emphasis on class imbalance, structural overlap, and robustness in graph-based classification tasks.
Random geometric graphs: I investigate the theoretical and computational properties of Proximity Catch Digraphs (PCDs), focusing on their construction, domination, density, and connectivity in both statistical and geometric contexts.
Network optimization and adversarial traversal: I design algorithms for stochastic and adversarial navigation problems, such as the Canadian Traveler’s Problem and the Stochastic Obstacle Scene Problem, addressing traversal under incomplete information and risk-aware constraints.
Spatial statistics: I apply nearest-neighbor and graph-based approaches to spatial clustering and point pattern analysis in ecological and simulated environments.
Statistical methods for biomedical datascience: I develop methods for modeling and inference in high-dimensional biomedical and neuroimaging data, with applications in disease diagnostics and brain morphometric analysis.